Professor Nikola Kasabov
Auckland University of Technology, New Zealand
Professor Nikola Kasabov Spiking Neural Networks, Deep Learning, and Brain-inspired Artificial Intelligence
ABSTRACT. Brain-inspired AI (BI-AI) is the contemporary phase in the AI development that is concerned with the design and implementation of highly intelligent machines that utilise information processing principles from the human brain, along with their applications. Spiking neural networks (SNN) and deep learning algorithms in SNN are brain-inspired techniques that make it possible for a new generation of AI systems to be developed - the brain-inspired AI (BI-AI).

This presentation has two parts. The first part covers generic methodological aspects of AI and neural networks, including: Adaptive learning of evolving processes in space and time; Data, Information and Knowledge; The human brain as a deep learning system; Classical methods of ANN; Methods of SNN; Deep learning in brain-inspired SNN architectures; Evolutionary and quantum-inspired optimisation of SNN systems; Neuromorphic development software and hardware platforms for SNN.

The second part presents specific methods, systems and applications based on deep learning in SNN and BI-AI for various problems and data, including: signal processing; audio/visual data for fast moving object recognition; multisensory predictive modelling of streaming data; cybersecurity. It concludes with discussions about the future of AI. A development software system NeuCube and application systems can be found on: http://www.kedri.aut.ac.nz/neucube/. Details of this presentation are included in [15].

REFERENCES:

  1. Kasabov, N. Neural networks and genetic algorithms. Avtomatika i Informatika, 8/9:51-60 (1990) (in Bulgarian)
  2. Kasabov, N. Incorporating neural networks into production systems and a practical approach towards the realisation of fuzzy expert systems. Computer Science and Informatics 21(2): 26-34 (1991)
  3. Kasabov, N. and Shishkov, S. A connectionist production system with partial match and its use for approximate reasoning. Connection Science 5(3/4): 275-305 (1993)
  4. Schliebs, S., Kasabov, N. (2013). Evolving spiking neural network-a survey. Evolving Systems, 4(2), 87-98.
  5. Kasabov, N. (2014) NeuCube: A Spiking Neural Network Architecture for Mapping, Learning and Understanding of Spatio-Temporal Brain Data, Neural Networks, 52, 62-76.
  6. Kasabov, N., Dhoble, K., Nuntalid, N., Indiveri, G. (2013). Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition. Neural Networks, 41, 188-201.
  7. Kasabov, N. et al (2016) A SNN methodology for the design of evolving spatio-temporal data machines, Neural Networks.
  8. Kasabov, N., et al. (2014). Evolving Spiking Neural Networks for Personalised Modelling of Spatio-Temporal Data and Early Prediction of Events: A Case Study on Stroke. Neurocomputing.
  9. Furber, S. et al (2012) Overview of the SpiNNaker system architecture, IEEE Trans. Computers, 99.
  10. Indiveri, G., Horiuchi, T.K. (2011) Frontiers in neuromorphic engineering, Frontiers in Neuroscience, 5.
  11. Scott, N., N. Kasabov, G. Indiveri (2013) NeuCube Neuromorphic Framework for Spatio-Temporal Brain Data and Its Python Implementation, Proc. ICONIP 2013, Springer LNCS, 8228, pp.78-84.
  12. Kasabov, N. (ed) (2014) Springer Handbook of Bio- and Neuroinformatics, Springer.
  13. EU Marie Curie EvoSpike Project (Kasabov, Indiveri): http://ncs.ethz.ch/projects/EvoSpike/
  14. NeuCube, http://www.kedri.aut.ac.nz/neucube/
  15. Kasabov, N (2018) Spiking Neural Networks, Deep learning and Brain-Inspired Artificial Intelligence, Springer, 450 pp.

ABOUT THE AUTHOR:
Professor Nikola Kasabov is a Fellow of IEEE, Fellow of the Royal Society of New Zealand, DVF of the Royal Academy of Engineering, UK and the Scottish Computer Association. He is the Director of the Knowledge Engineering and Discovery Research Institute (KEDRI), Auckland and Professor at the School of Engineering, Computing and Mathematical Sciences at Auckland University of Technology. Kasabov is President-Elect of the Asia Pacific Neural Network Society (APNNS) to serve as the President in 2019. He is a Past President of the International Neural Network Society (INNS) and APNNS. He is a member of several technical committees of IEEE Computational Intelligence Society and a Distinguished Lecturer of the IEEE CIS (2012-2014). He is a Co-Editor-in-Chief of the Springer journal Evolving Systems and serves as Associate Editor of Neural Networks, IEEE TrNN, -Tr CDS, -TrFS, Information Science, Applied Soft Computing and other journals. Kasabov holds MSc and PhD from the TU Sofia, Bulgaria. His main research interests are in the areas of neural networks, intelligent information systems, soft computing, bioinformatics, neuroinformatics. He has published more than 600 publications that include 15 books, 220 journal papers, 28 patents and numerous chapters and conference papers.

He has extensive academic experience at various academic and research organisations in Europe and Asia, including: TU Sofia Bulgaria; University of Essex UK; University of Otago, NZ, Advisor Professor at the Shanghai Jiao Tong University, Visiting Professor at ETH/University of Zurich and Robert Gordon University in the UK. Prof. Kasabov has received a number of awards, among them: the APNNA ‘Outstanding Achievements Award’; the INNS Gabor Award for ‘Outstanding contributions to engineering applications of neural networks’; the EU Marie Curie Fellowship; the Bayer Science Innovation Award; the APNNA Excellent Service Award; the RSNZ Science and Technology Medal; the 2015 AUT Medal for outstanding academic contribution; Honorable Member of the Bulgarian Academic Society for Computer Science and IT, and others. He is an Honorary Citizen of Pavlikeni and a Mentor of the “Bacho Kiro” school in the town. He has supervised to completion 46 PhD students. More information of Prof. Kasabov can be found on the KEDRI web site.